Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1296 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0002

Data Index: 228674 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0793. Min Act: -0.0002

Data Index: 539982 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0767. Min Act: -0.0002

Data Index: 97854 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0774. Min Act: -0.0002

Data Index: 619317 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0822. Min Act: -0.0002

Data Index: 998412 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0731. Min Act: -0.0002

Data Index: 508739 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0730. Min Act: -0.0002

Data Index: 215724 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1000141 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0728. Min Act: -0.0002

Data Index: 674250 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0720. Min Act: -0.0001

Data Index: 973462 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1060526 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0707. Min Act: -0.0002

Data Index: 373873 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0689. Min Act: -0.0002

Data Index: 513693 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0702. Min Act: -0.0002

Data Index: 335980 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1338952 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1197324 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0704. Min Act: -0.0002

Data Index: 733707 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0716. Min Act: -0.0002

Data Index: 890162 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0694. Min Act: -0.0002

Data Index: 187316 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0696. Min Act: -0.0002

Data Index: 720915 (C4 (Web Text))

Max Activating Token Index: 125